Prediction of the Risk Types of Human Papillomaviruses by Support Vector Machines

摘要: Infection by high-risk human papillomaviruses (HPVs) is associated with the development of cervical cancers. Classification risk types important to understand mechanisms in infection and develop novel instruments for medical examination such as DNA microarrays. In this paper, we classify type HPVs using protein sequences. Our approach based on hidden Markov model Support Vector Machines. The former searches informative subsequence positions latter computes efficiently experiments, proposed classifier was compared previous methods accuracy F-cost, also prediction result four unknown presented.